Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of reporting on finding deceased individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "found" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.75
     tert
    -0.73
    creation
    -0.72
    dayName
    -0.70
    dos
    -0.64
    ankind
    -0.63
    entric
    -0.61
    annis
    -0.61
    adan
    -0.60
    idium
    -0.60
    POSITIVE LOGITS
    Ô
    0.88
    âĸĪ
    0.81
     guilty
    0.80
    dylib
    0.80
    ت
    0.79
    س
    0.74
    adle
    0.72
    mint
    0.71
     Guilty
    0.71
     dead
    0.70
    Act Density 0.036%

    No Known Activations